selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

ConwayResearch logo

Underdog-Woof

ConwayResearch·released 5 Nov 2026

underdog-non-commercial-1.0? GB
Your GPU
hf download ConwayResearch/Underdog-Woof
Setup ↓

Underdog Woof is a small English text-to-speech model with two voices: Juno and Mira. It reads phone numbers, dates, prices and codes the way people say them, and it runs on a laptop CPU with nothing but numpy, from a single 40.6 MB file. Try it in your browser at underdog.ai/woof.

How much VRAM does Underdog-Woof need?

--vram
any
--gpus
--quant

The parameter count of this model is unknown, so there is no memory estimate yet.

Run Underdog-Woof locally

No runtime support recorded yet. Most models also run through Hugging Face Transformers.

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
cowWhySo/Underdog-Woof-MLXMLX——16
masterofaudio2077/underdog-woof-onnxONNX———

About Underdog-Woof

Underdog Woof is a small English text-to-speech model with two voices: Juno and Mira. It reads phone numbers, dates, prices and codes the way people say them, and it runs on a laptop CPU with nothing but numpy, from a single 40.6 MB file. Try it in your browser at underdog.ai/woof. Each voice reads "Please call me back at 415-555-0199 before 5:30 p.m. on Friday." (seed 1). More clips are in the samples folder, listed below. Woof comes in two sizes. This repo is the two-voice model. The one-voice model is the one that runs in your browser at underdog.ai/woof. The one-voice speed is plain PyTorch with its int8 weights at the default 16 steps; the two-voice speed is this repo's numpy runtime. Fish Audio Drama 3, for scale, is a 41.5 GB download and gets 1.89% wrong. Word error rate on Gradium TTS Hard Cases (English, 500 sentences), every model run and scored by us the same way, each in its best-scoring voice. Lower is better. Kitten Nano 0.8 is the only smaller download, and it gets 9.81% of words wrong: nothing we tested is both smaller and more accurate than Woof. Transcripts by qwen3.8-omni-flash, word errors counted by gemma-4-31b-it. Download is the smallest official set of weights each model needs to run, from its Hugging Face repo in November 2026 (Phonon 31m: the 4-bit GGUF; Kitten Nano: the int8 ONNX plus voices; Pocket TTS: the English model; Qwen3-TTS: the model plus its speech tokenizer). Cloud-only models don't publish a size.

Full model card on Hugging Face →

Alternatives to Underdog-Woof

All alternatives →
k2-fsa logo

OmniVoice

k2-fsa·TTS

≈1.9 GB

OmniVoice is a massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it delivers high-quality speech with superior inference speed, supporting voice cloning and voice design.

613MUnknown licence
4.2MMar 2026gguf
openbmb logo

VoxCPM2

openbmb·TTS

≈5.6 GB

VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data.

2.3BApache 2.0
971.2KApr 2026gguf

Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs.

1.9BApache 2.0
1.1MJan 2026gguf
Qwen logo≈2.5 GB

Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.

915MApache 2.0
839.5KJan 2026gguf
hexgrad logo

Kokoro-82M

hexgrad·TTS

≈0.7 GB

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.

82MApache 2.0
13.1MDec 2024gguf

Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.

906MApache 2.0
715.7KJan 2026gguf

Underdog-Woof FAQ

Can I use Underdog-Woof commercially?
No. It is released under underdog-non-commercial-1.0. Custom licence: read the model card before using it commercially.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.